Skip to main content
A skill is a written procedure the server can hand a model when a question matches it — which endpoints to call in which order, how to weigh conflicting signals, and how to format the result. It is loaded on demand rather than sitting in every prompt, for the same reason the tool schemas are discovered rather than enumerated. Ask a concrete question; the agent can load the matching workflow on demand. The shared workflow bundle has five entrypoints, with deeper specialist guidance available as needed: The four Solutions workflows connect these steps to real REST requests. Ordinary MCP resource access and tool-only resource fallbacks use the same packaged content. Skill import is supported where the client offers it; an imported skill is a release snapshot and must be reimported for updates. Preparing an import bundle does not imply app-directory publication. Public coding-plugin versions may lag the server bundle; check the installed release. Existing entrypoints such as gdelt-discover-and-drill, brief-output, multi-surface-synthesis, macro-native and prediction-markets remain available for compatibility and specialist guidance.

The one that matters most

gdelt-discover-and-drill encodes the habit this API rewards: start wide, then narrow into what the summary actually showed. A narrow first query returns an empty result that reads as “nothing happened” when it means “these filters intersected to nothing” — and a model with no procedure will usually take the empty result at face value. The same loop written out by hand is in Answer a question with MCP. The brief-output skill remains available for formatting your own cited answer. Hosted Monitoring Brief generation is temporarily unavailable.

External tools

The third-party providers some skills reach for, and what they are and are not.